通过剪枝与低成本替换，让多智能体系统更省 token 且不丢性能。
AgentSlimming: Towards Efficient and Cost-Aware Multi-Agent Systems
- 用混合机制评估每个智能体重要性，再剪掉冗余或替换成低成本智能体。
- 平均减少 78.9% 的 token 消耗，性能几乎不变甚至提升。
- 适合追求高效、低成本多智能体系统的开发者使用。
基于大语言模型的多智能体系统在复杂任务中表现出色，但人工设计最优通信拓扑费时，自动化扩展常导致结构臃肿、智能体冗余，造成过高 token 消耗。为此，我们提出 extbf{AgentSlimming}，一个即插即用的图结构多智能体工作流压缩框架。受神经网络剪枝与量化启发，AgentSlimming 先通过混合机制估算每个智能体的重要性得分，再移除冗余智能体或替换为低成本版本，每一步操作均通过基准锚定的接受准则验证，防止性能崩溃。实验表明，AgentSlimming 最高可降低 78.9% 的平均 token 消耗，性能几乎无损，甚至有时提升准确率，实现成本与质量的强帕累托最优平衡。代码已公开于 https://github.com/CitrusYL/AgentSlimming。
原文摘要 · Abstract (English)
Large Language Model-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex tasks. However, manually designing optimal communication topologies is labor-intensive, while automated expansion methods often result in bloated structures with redundant agents, leading to excessive token consumption. To address this problem, we introduce \textbf{AgentSlimming}, a plug-and-play compression framework for graph-structured multi-agent workflows. Motivated by pruning and quantization in neural networks, AgentSlimming compresses workflows by first estimating the importance score of each agent with a hybrid mechanism, and then removes redundant agents or replaces them with low-cost ones, where each operation is validated using a baseline-anchored acceptance rule to prevent performance collapse. Experiments show that AgentSlimming reduces average token cost by up to 78.9\% with negligible performance degradation, and sometimes even improves accuracy, achieving a strong Pareto-optimal trade-off between cost and quality. \textit{Our code is publicly available at https://github.com/CitrusYL/AgentSlimming
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。